This paper studies the use of discrete-time recurrent neural networks for predicting the next symbol in a sequence. The focus is on online prediction, a task much harder than the c...
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
We propose a genetic ensemble of recurrent neural networks for stock prediction model. The genetic algorithm tunes neural networks in a two-dimensional and parallel framework. The ...
Neurodynamical models of working memory (WM) should provide mechanisms for storing, maintaining, retrieving, and deleting information. Many models address only a subset of these a...
Recurrent neural networks fail to deal with prediction tasks which do not satisfy the causality assumption. We propose to exploit bi-causality to extend the Recurrent Cascade Corr...